# Revisiting Rotation Averaging: Uncertainties and Robust Losses

arXiv: https://arxiv.org/abs/2303.05195 · HTML: https://mlsanity.com/paper/2303.05195/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 40 references that are in the map.
- First posted on arXiv 9 Mar 2023.

## Builds on (most cited first, 3 of 3)

- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Shonan Rotation Averaging: Global Optimality by Surfing SO(p)n](https://mlsanity.com/paper/2008.02737/) (2020)

## Built on by (most cited first, 18 of 18)

- [Global Structure-from-Motion Revisited](https://mlsanity.com/paper/2407.20219/) (2024)
- [SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs](https://mlsanity.com/paper/2404.00469/) (2024)
- [ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association](https://mlsanity.com/paper/2509.01584/) (2025)
- [Advances in Global Solvers for 3D Vision](https://mlsanity.com/paper/2602.14662/) (2026)
- [Fed3DGS: Scalable 3D Gaussian Splatting with Federated Learning](https://mlsanity.com/paper/2403.11460/) (2024)
- [GlobalPointer: Large-Scale Plane Adjustment with Bi-Convex Relaxation](https://mlsanity.com/paper/2407.13537/) (2024)
- [Distributed Global Structure-from-Motion with a Deep Front-End](https://mlsanity.com/paper/2311.18801/) (2023)
- [Towards Initialization-free Calibrated Bundle Adjustment](https://mlsanity.com/paper/2506.23808/) (2025)
- [Gravity-aligned Rotation Averaging with Circular Regression](https://mlsanity.com/paper/2410.12763/) (2024)
- [Certifiably Optimal Anisotropic Rotation Averaging](https://mlsanity.com/paper/2503.07353/) (2025)
- [A Taxonomy of Structure from Motion Methods](https://mlsanity.com/paper/2505.15814/) (2025)
- [Incremental Rotation Averaging Revisited](https://mlsanity.com/paper/2309.16924/) (2023)
- [LOSTU: Fast, Scalable, and Uncertainty-Aware Triangulation](https://mlsanity.com/paper/2311.11171/) (2023)
- [PRAGO: Differentiable Multi-View Pose Optimization From Objectness Detections](https://mlsanity.com/paper/2403.08586/) (2024)
- [Multiple Rotation Averaging with Constrained Reweighting Deep Matrix Factorization](https://mlsanity.com/paper/2409.09790/) (2024)
- [Making Rotation Averaging Fast and Robust with Anisotropic Coordinate Descent](https://mlsanity.com/paper/2506.01940/) (2025)
- [MGSfM: Multi-Camera Geometry Driven Global Structure-from-Motion](https://mlsanity.com/paper/2507.03306/) (2025)
- [HETA++: Global Structure-from-Motion with Hybrid Explicit Translation Averaging](https://mlsanity.com/paper/2607.15912/) (2026)

## Abstract (arXiv)

In this paper, we revisit the rotation averaging problem applied in global Structure-from-Motion pipelines. We argue that the main problem of current methods is the minimized cost function that is only weakly connected with the input data via the estimated epipolar geometries.We propose to better model the underlying noise distributions by directly propagating the uncertainty from the point correspondences into the rotation averaging. Such uncertainties are obtained for free by considering the Jacobians of two-view refinements. Moreover, we explore integrating a variant of the MAGSAC loss into the rotation averaging problem, instead of using classical robust losses employed in current frameworks. The proposed method leads to results superior to baselines, in terms of accuracy, on large-scale public benchmarks. The code is public. https://github.com/zhangganlin/GlobalSfMpy